A fork of Handy by CJ Pais, developed by Abdullah Al Kulaib
open beta
Win · macOS · Linux · Android
Open source
On-device speech to text

Speak.
It’s text.

Speech-to-text runs locally on your device after the selected model is downloaded. Press a hotkey, talk, and your words land in the active text field. Model downloads, update checks and optional external AI text processing can use a network connection.

Rec0:00·⌥ Space
01

Reply to the team that the build is green and shipping at noon.

Models:Whisper · Parakeet · Moonshine · Sense-Voice · Canary · Giga-AM · Breeze · Cohere
01Features

Built for quick, everyday dictation.

01

Local transcription

After the selected speech model is downloaded, the speech-to-text step runs locally on your device.

02

Works in any application

A global hotkey drops text into editors, browsers, chat, email, wherever the cursor is.

03

Your models, your choice

Swap open ASR models (Whisper, Parakeet, Moonshine and more) to balance speed and accuracy.

04

Cross-platform, native

Windows, macOS on Apple Silicon, Linux on Ubuntu / Debian, and Android.

05

Free and open source

Read the source, file an issue, or build the application yourself.

02How it works
01

Press your hotkey

A global shortcut starts listening from anywhere, no window to switch to.

02

Speak naturally

Talk as you normally would. After the model is downloaded, Verbatim transcribes locally on your device.

03

Your text appears

Words type straight into whatever app you’re in. Release to stop.

03Privacy

Local transcription, with clear choices for optional external processing.

[ local transcription on your device ]
01Local transcription keeps the speech-to-text step on your device after the selected model is downloaded.
02Downloading models and updates requires a network connection.
03If you enable an external provider for optional AI processing, the text needed for that feature is sent to that provider.
04Review the setting and the provider's privacy policy before enabling external processing.
04FAQ

Questions, answered.

01

Is Verbatim really free?

Yes. Free and open source, no subscription, no account. The full source is on GitHub.

02

Where does transcription happen?

After the selected model is downloaded, the speech-to-text step runs locally on your device. Optional external AI processing is separate and may send the text needed for that feature to the provider you configure.

03

Why does my OS warn on first launch?

The build is unsigned. On Windows: More info → Run anyway. On macOS: right-click → Open. One time only.

04

Does it work offline?

Local transcription can run after the selected model is downloaded. Model downloads, update checks and any external AI provider you enable require a network connection.

05

Can I change the hotkey or model?

Yes. Set any global hotkey, and switch between open models (Whisper, Parakeet, Moonshine, and more) in settings.

06

Which platforms are supported?

Windows (x64), macOS (Apple Silicon), Linux (Ubuntu/Debian), and Android (sideloaded APK).

05Download

Get Verbatim.

free & open source · What’s new

All releases & checksums ↗ · Desktop builds are unsigned; SmartScreen / Gatekeeper may warn on first launch (More info → Run anyway, or right-click → Open). The Android APK is signed.

Android: download on your phone and tap the APK to install (allow installs from unknown sources if asked). If a download sticks at 100%, switch networks or try another browser.